Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Scaling Karpathy's Autoresearch: What Happens When the Agent Gets a GPU Cluster

blog.skypilot.co

Post reply on HN
Print view View original

71–80 of 126 posts

Re: Scaling Karpathy's Autoresearch: What Happens When the Agent Gets a GPU Cluster

#71

Post by falcor84 »

ipsum2 wrote: post #10
kraddypatties wrote: post #2

I feel like most of this recent Autoresearch trend boils down to reinventing hyper-parameter tuning. Is the SOTA still Bayesian optimization when given a small cluster? It was ~3 years ago when I was doing this kind of work, haven't kept up since then. Also, shoutout SkyPilot! It's been a huge help for going multi-cloud with our training and inference jobs (getting GPUs is still a nightmare...)!

Hyperparam tuning that has better intuition and can incorporate architecture changes automatically. It won't invent something completely new though.

> It won't invent something completely new though.

I don't necessarily disagree, but am wondering whether you have any particular reason/intuition driving you to claim this. I have seen AI agents be quite creative in other tasks; do you think there's a particular reason why we shouldn't see creativity in architecture research, given enough time and resources?

Re: Scaling Karpathy's Autoresearch: What Happens When the Agent Gets a GPU Cluster

#72

Post by Drupon »

karpathy wrote: post #15
kraddypatties wrote: post #2

I feel like most of this recent Autoresearch trend boils down to reinventing hyper-parameter tuning. Is the SOTA still Bayesian optimization when given a small cluster? It was ~3 years ago when I was doing this kind of work, haven't kept up since then. Also, shoutout SkyPilot! It's been a huge help for going multi-cloud with our training and inference jobs (getting GPUs is still a nightmare...)!

Wrong and short-sighted take given that the LLM explores serially learning along the way, and can tool use and change code arbitrarily. It seems to currently default to something resembling hyperparameter tuning in absence of more specific instructions. I briefly considered calling the project “autotune” at first but I think “autoresearch” will prove to be the significantly more appropriate name.

tfw le AI guy has LLM psychosis. We're cooked

Re: Scaling Karpathy's Autoresearch: What Happens When the Agent Gets a GPU Cluster

#73

Post by viccis »

chaos_emergent wrote: post #14
covi wrote: post #4

This feels like the chimpanzee with a power drill. An agent is honestly just brute-force search, but guided.

Human-driven research is also brute-force but with a more efficient search strategy. One can think of a parameter that represents research-search-space-navigation efficiency. RL-trained agents will inevitably optimize for that parameter. I agree with your statement insomuch as the value of that efficiency parameter is lower for agents than humans today. It's really hard to imagine that they __won't__ exceed the human…

>Human-driven research is also brute-force but with a more efficient search strategy

No it's not. Is there anything to back that up? There's a creative aspect to human research that I've yet to see with gen AI. All it does is regurgitate stuff and get some "new" ideas via the latent space of the distribution it models. But a generative model cannot by definition create anything new. Just estimate its data well enough that it can sample it well enough to fake novelty.

Re: Scaling Karpathy's Autoresearch: What Happens When the Agent Gets a GPU Cluster

#74

Post by SirensOfTitan »

nfg wrote: post #27
saberience wrote: post #25

Earlier quoted context omitted.

Have you actually used LLMs for non trivial tasks? They are still incredibly bad when it comes to actually hard engineering work and they still lie all the time, it's just gotten harder to notice, especially if you're just letting it run all night and generate reams of crap. Most people are optimizing for terrible benchmarks and then don't really understand what the model did anyone and just assume it did something g…

Do you realise who you’re replying to?

I think the OP's comment is entirely fair. Karpathy and others come across to me as people putting a hose into itself: they work with LLMs to produce output that is related to LLMs.

I might reframe the comment as: are you actually using LLMs for sustained, difficult work in a domain that has nothing to do with LLMs?

It feels like a lot of LLM-oriented work is fake. It is compounding "stuff," both inputs and outputs, and so the increased amount of stuff makes it feel like we're living in a higher plane of information abundance, but in reality we're increasing entropy.

Tech has always had an information bias, and LLMs are the perfect vehicle to create a lot of superfluous information.

Re: Scaling Karpathy's Autoresearch: What Happens When the Agent Gets a GPU Cluster

#77

Post by janalsncm »

karpathy wrote: post #15
kraddypatties wrote: post #2

I feel like most of this recent Autoresearch trend boils down to reinventing hyper-parameter tuning. Is the SOTA still Bayesian optimization when given a small cluster? It was ~3 years ago when I was doing this kind of work, haven't kept up since then. Also, shoutout SkyPilot! It's been a huge help for going multi-cloud with our training and inference jobs (getting GPUs is still a nightmare...)!

Wrong and short-sighted take given that the LLM explores serially learning along the way, and can tool use and change code arbitrarily. It seems to currently default to something resembling hyperparameter tuning in absence of more specific instructions. I briefly considered calling the project “autotune” at first but I think “autoresearch” will prove to be the significantly more appropriate name.

I think we need to separate theory from practice. In theory, it can edit the training loop and come up with novel techniques. That is interesting.

In practice, the vast majority of the changes that auto research actually made would have been found much faster with BO if properly parameterized. You do not need an LLM to find a better batch size or learning rate.

Re: Scaling Karpathy's Autoresearch: What Happens When the Agent Gets a GPU Cluster

#78

Post by caconym_ »

anon291 wrote: post #55
caconym_ wrote: post #40

Earlier quoted context omitted.

I honestly don't think I have. In this case, using a cheap(er) signal or heuristic as an initial filter before spending more resources on cases that pass the filter is a pattern that shows up all over the place, and LLMs are good at picking up on patterns like that and generalizing them. AFAICT.

I'm not sure how people say this so confidently. I have a rather esoteric haskell library that I've written and published for years. ChatGPT and Claude both know about it and frequently help me improve it, and propose completely novel approaches. I'm really not sure how people are so confident that they can't think of anything new. This seems like wishful confirmation bias.

> I'm not sure how people say this so confidently.

Say what, exactly?

Re: Scaling Karpathy's Autoresearch: What Happens When the Agent Gets a GPU Cluster

#79

Post by prpl »

janalsncm wrote: post #77
karpathy wrote: post #15

Earlier quoted context omitted.

Wrong and short-sighted take given that the LLM explores serially learning along the way, and can tool use and change code arbitrarily. It seems to currently default to something resembling hyperparameter tuning in absence of more specific instructions. I briefly considered calling the project “autotune” at first but I think “autoresearch” will prove to be the significantly more appropriate name.

I think we need to separate theory from practice. In theory, it can edit the training loop and come up with novel techniques. That is interesting. In practice, the vast majority of the changes that auto research actually made would have been found much faster with BO if properly parameterized. You do not need an LLM to find a better batch size or learning rate.

I’d always hoped something like this could take advantage of FPGAs directly

Re: Scaling Karpathy's Autoresearch: What Happens When the Agent Gets a GPU Cluster

#80

Post by hgoel »

This is fascinating to me because I just recently built something similar (as a test), not for improving AI, instead it's for tuning hyperparameters for a physics simulation.

We've managed to optimize execution of the simulation enough that brute-force search is a viable option, but giving an agent some background on how we tune those parameters on intuition and some physical reasoning, and a means to run tests and retrieve resulting statstics, works surprisingly well.

I see it as essentially a hyperparameter search that is more capable of finding and exploiting implicit constraints in a system.

Post reply on HN